AI RESEARCH
Residual Gaussian Splatting for Ultra Sparse-View CBCT Reconstruction
arXiv CS.CV
•
ArXi:2604.27552v1 Announce Type: new While 3D Gaussian splatting (3DGS) offers explicit and efficient scene representations for cone-beam computed tomography reconstruction, conventional photometric optimization inherently suffers from spectral bias under ultra sparse-view conditions, leading to over-smoothing and a loss of high-frequency anatomical details. Since wavelet transforms provide rich high-frequency information and have been widely utilized to enhance sparse reconstruction, this work integrates wavelet multi-resolution analysis with 3.